Skip Navigation
Skip to contents

ACC : Acute and Critical Care

OPEN ACCESS
SEARCH
Search
Advanced Search
mobile menu button

Articles

Page Path
HOME > Acute Crit Care > Volume 41(2); 2026 > Article
Review Article
Pediatrics From scores to signals: evolution and innovations in pediatric early warning systems
Acute and Critical Care 2026;41(2):252-261.
DOI: https://doi.org/10.4266/acc.004475
Published online: May 19, 2026

1Department of Pediatrics, Seoul National University Hospital, Seoul, Korea

2Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Korea

Corresponding author: Bongjin Lee Department of Pediatrics, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Korea Tel: +82-2-2072-3568 Fax: +82-2-747-5130 Email: pedbjl@snu.ac.kr
• Received: September 23, 2025   • Revised: February 9, 2026   • Accepted: February 11, 2026

© 2026 The Korean Society of Critical Care Medicine

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

  • 1,133 Views
  • 33 Download
prev next
Full Article

Download PDF Download PDF

  • Early identification of clinical deterioration in hospitalized children is essential to improve outcomes and prevent critical events. Over the past two decades, structured approaches such as pediatric early warning scores and rapid response systems have provided a framework for systematic risk detection in general wards. More recently, artificial intelligence and continuous monitoring technologies have begun to transform this field, offering the potential for more timely and accurate recognition of subtle changes in patient status. Despite these advances, challenges remain before seamless integration of these technologies into routine clinical decision-making can be achieved. This review explores the evolution of pediatric early warning systems and examines how emerging innovations may shape the future of predictive monitoring and clinical decision support in pediatric care.
  • Key Words: artificial intelligence; hospital rapid response team; monitoring, physiologic measurements; patient safety; pediatrics
Early recognition of clinical deterioration in pediatric patients admitted to general wards is associated with improved outcomes by preventing critical events such as cardiac arrest, unplanned intensive care unit (ICU) admission, or even death [1-4]. However, detecting early signs of decline in hospitalized children is often challenging. This difficulty is largely due to physiological variability in pediatric patients and their limited ability to clearly express symptoms [3,5-7]. These factors can lead to missed or misinterpreted warning signs indicating sudden deterioration, resulting in delayed interventions and, consequently, poor outcomes [5-7].
Rapid response systems (RRS) have been introduced in response to these challenges. The primary goal of RRS is to facilitate early identification and prompt intervention before deterioration becomes life-threatening for patients in non-critical care settings. To achieve this goal, hospitals worldwide have invested in implementing, refining, and evaluating RRS over the past two decades, and these systems continue to evolve [8]. This narrative review explores approaches to enhance the early detection of clinical deterioration, focusing on the development of structured systems by examining key historical publications and summarizing recent technological advances in pediatric patient monitoring through a review of the most contemporary studies indexed in PubMed.
The development of effective early detection strategies for clinical deterioration in pediatric patients has been a progressive endeavor (Table 1). Early initiatives were motivated by the recognition that observable physiological changes typically precede critical events by several hours in both adult and pediatric populations [5,7,9]. This interval serves as an opportunity for healthcare providers to intervene proactively and potentially alter the clinical trajectory during admission. Furthermore, evidence shows that factors contributing to critical events are often avoidable. For example, a study in the United Kingdom estimated that a significant proportion of pediatric in-hospital deaths involved potentially avoidable contributing factors, with figures approaching 50% [10,11]. Such findings have spurred the development and implementation of structured early warning systems.
Initial early warning systems were adapted from adult systems, such as the Modified Early Warning Score [5]. However, these early tools proved to be inadequate for pediatric populations due to children’s unique and variable physiology, requiring different thresholds and considerations for children. In response, pediatric-specific systems were developed. The Brighton Pediatric Early Warning Score (PEWS) [5] and Duncan et al.’s [12] PEWS in the early 2000s were among the first to systematically combine vital signs and clinical observations such as behavior and respiratory effort into composite scores. These systems formalized the early warning model, which relies on regular monitoring of patient status, structured assessment, and predefined intervention protocols triggered when concerning patterns appear in hospitalized patients.
As the field progressed, two distinct types of systems became mainstays of operationalizing the early warning approach: parameter-based activation and scoring-based activation [10]. Parameter-based systems, like the Bristol PEWS and the Medical Emergency Team Activation Criteria in Australia, trigger an alert when any physiological measure exceeds a predefined threshold [10,13,14]. In contrast, scoring-based systems, such as the Cardiac Children’s Hospital Early Warning Score and the Bedside PEWS combine physiological measurements and clinical observations into a single composite score that stratifies patient risk and determines the appropriate level of response [10,15,16]. While these systems differ in design, thresholds, and complexity, they share a common goal of improving the timely detection of deterioration of pediatric patients admitted to general wards (Table 2) [3,5,12-16]. Importantly, these tools were developed within heterogeneous clinical environments and therefore differ in intended scope. Some were optimized for general ward surveillance, whereas others reflect population-specific priorities or institutional workflows, such as cardiovascular-focused parameters in cardiac care settings.
Increasingly, such scoring systems have been integrated within broader RRS frameworks, implicitly acknowledging that detection alone is insufficient without timely response and system-wide support [17]. Modern RRS frameworks were refined to include four key components: an afferent limb for detection, an efferent limb for response, a supporting structure for ongoing quality improvement, and governance to oversee system function [11]. Examples of RRS implementation in pediatric hospitals include the Acute Response System described by Jeon et al. [3] in South Korea, which significantly reduced life-threatening events outside the ICU, and the Bedside PEWS integrated into a quality improvement initiative in Saudi Arabia, which improved the timeliness of ICU transfers and overall patient outcomes [1]. Additionally, large-scale initiatives like the National Health Service 100,000 Lives Campaign in the United Kingdom further accelerated the adoption of structured RRS incorporating PEWS across multiple hospitals [18]. These collective efforts highlight how early warning tools have evolved not in isolation but as part of broader institutional strategies to enhance pediatric patient safety in non-critical care settings.
Despite decades of development and widespread adoption, debate persists regarding the real-world effectiveness of early warning systems. While some studies have shown encouraging results following implementation of RRS, systematic reviews and meta-analyses suggest that overall effectiveness remains inconsistent across settings [7,8,10].
Among the studies that reported encouraging results, Jeon et al. [3] found that RRS implementation over a period of 11 years decreased CPR and unplanned ICU admission rates in the general ward. Similarly, Al-Harbi [1] observed that implementing RRS was associated with a reduction in cardiac arrests of 1.64 fewer incidents per unit time, alongside a drop of 9.61 unplanned ICU admissions per unit time with statistical significance. AlZaher et al. [2] found that embedding the Bedside PEWS in daily clinical practice facilitated earlier escalation of care, resulting in reduced mortality rate after unplanned ICU admission from 1.3 per 100 bed days to 0.4 per 100 bed days.
However, systematic reviews by Trubey et al. [7] and Chapman et al. [10] and a meta-analysis done by Maharaj et al. [8] have highlighted variability in RRS effectiveness across hospitals and countries due to differences in staff training, adherence to protocol, and patient demographics. Additionally, over 30 different PEWS variants are in use globally, each with unique scoring methods and thresholds, complicating direct comparisons and limiting standardization [7,19,20]. For these reasons, experts have argued that PEWS should not be viewed as a standalone solution but rather as part of a broader socio-technical system that includes staff engagement, strong governance, and continuous quality improvement [7].
Another persistent limitation beyond these systemic challenges is the trade-off between sensitivity and specificity: highly sensitive PEWS can cause alarm fatigue through excess false positives, whereas systems tuned for specificity may fail to identify early signs of deterioration [7]. Other issues include inconsistent activation of RRS protocols by medical staff even when PEWS thresholds are crossed and concerns that over-reliance on numeric scores may erode clinical judgment [10,11]. Moreover, the dependence of PEWS on manually calculated scores based on static criteria may delay recognition of subtle physiological changes. These inherent constraints have prompted researchers and clinicians to seek more adaptive, data-driven solutions that move beyond intermittent, static score-based assessment and operate in real time (Figure 1).
To overcome the limitations of static, rule-based PEWS, recent research has shifted toward artificial intelligence (AI) and machine learning approaches capable of leveraging high-dimensional electronic medical record data. An AI-based early warning system generally refers to a predictive model that continuously analyzes large volumes of clinical data such as vital signs and laboratory results to identify patterns associated with impending deterioration. Unlike traditional scoring systems that rely on fixed thresholds and limited parameters, these models can integrate numerous variables, capture complex and non-linear relationships, and update risk assessments dynamically as new data become available.
Foote et al. [21] developed and internally validated a machine learning model for predicting pediatric deterioration events, achieving an area under the receiver operating curve of 0.85, outperforming traditional PEWS (area under the receiver operating curve [AUROC], 0.69); this model enabled earlier detection of deterioration by up to a median of 8 hours. In Korea, Jeon et al. [22] proposed a deep learning model for predicting critical events in general wards, reporting an AUROC of 0.99 and an area under the precision-recall curve (AUPRC) of 0.9, demonstrating both excellent discrimination and balance between sensitivity and specificity. However, these models have so far only undergone internal validation, with more evidence of their generalizability required.
Park et al. [23] reported an AUROC of 0.92 for cardiopulmonary arrest and 0.91 for unplanned ICU transfers using a deep learning-based pediatric early warning system. Their model also reduced false alarms by up to 82%, improving precision and mitigating alarm fatigue compared to traditional PEWS. An effort to externally validate this model was undertaken by Shin et al. [6], who conducted a multicenter study and demonstrated that the model had an improved AUROC of 0.8 compared to 0.76 for traditional PEWS. While external validation showed some performance drop compared to internal validation, this model still outperformed traditional PEWS, highlighting its potential practical value. This model has since been deployed in clinical practice and is commercially available (DeepCARS; VUNO).
Adult hospitals have a longer and more established history of developing AI-driven RRS, providing an important roadmap for pediatric translation. Over the past decade, several AI-based deterioration prediction models have been created and retrospectively validated at scale in adult inpatient settings [24,25]. Beyond retrospective validation, some adult systems have already progressed to prospective evaluation. For example, Cho et al. [26] prospectively implemented the Deep Learning-based Cardiac Arrest Risk Management System across four hospitals in Korea and reported consistently superior performance compared with conventional early warning systems. The adult studies illustrate both the feasibility and clinical impact of AI-driven RRS, and adult systems can provide an important foundation for developing AI-based models tailored to pediatric care.
Still, pediatric studies lack external validation, raising concerns about generalizability to diverse pediatric populations and clinical environments [8,11]. Moreover, while pediatric AI models often report high AUROC values, corresponding AUPRC metrics, which better reflect performance in detecting rare deterioration events, are sometimes low or omitted altogether. Although AI models show promise due to their use of real-world data, the absence of validated pediatric models using appropriate performance metrics limits clarity about their true impact on false alarms and missed detections. The ability to integrate AI-driven RRS seamlessly into existing pediatric clinical workflows is also essential, especially given that pediatric patient characteristics and ward workflows differ substantially from those in adult care settings.
In addition to these validation and implementation challenges, many AI-based prediction models continue to rely on intermittently updated clinical data feeds rather than continuously streamed physiological data, which means predictions may not capture real-time changes in patient status. Likewise, most models depend on aggregated variables rather than raw, high-resolution waveforms, potentially missing subtle patterns that may precede overt deterioration. These factors point to the need for next-generation innovations that integrate continuous, high-fidelity biosignal monitoring with AI analytics, an approach that has the potential to provide earlier and more precise alerts.
Building on this need, recent advancements in real-time biosignal analysis powered by AI are opening new frontiers for the early and accurate detection of clinical deterioration in pediatric patients. Unlike conventional systems that rely primarily on periodically recorded vital signs or observational assessments, continuous biosignal monitoring captures dynamic physiological fluctuations in real time, providing richer and temporally granular data [27,28]. This continuous data stream allows predictive models to detect subtle or transient patterns that may remain undetected in periodically measured data, ultimately improving early warning performance [28].
Continuous, high-fidelity biosignal analytics have traditionally been developed and validated within ICU settings because invasive lines are frequently placed in ICU patients and high sampling-rate monitoring data with detailed physiologic annotations are typically available. The ICU environment has served as an ideal testbed for advancing real-time signal processing and AI methods, and algorithms developed using ICU-acquired biosignals are transferable to the general ward because the underlying signal sources studied in the ICU can be acquired through widely available bedside monitors. Thus, while the methodological roots of biosignal AI lie in the ICU, its practical applications can be expanded toward ward-based early warning systems, helping bridge the gap between intermittent vital sign assessment and real-time physiologic monitoring.
Several studies have illustrated the clinical potential of biosignal AI (Table 3) [29-38]. For example, Duncan et al. [31] developed the Real-time Adaptive Predictive Indicator of Deterioration (RAPID) Index, an early warning system that continuously monitors heart rate and respiratory rate. While the traditional PEWS showed better overall predictive discrimination, the RAPID Index identified a higher proportion of significant clinical deterioration events, with a sensitivity of 97.2% compared to the 86.1% sensitivity of PEWS [31]. Similarly, Lee et al. [35] applied deep learning to continuous heart rate variability data in the ICU, achieving an AUROC of 0.89 for predicting impending cardiac arrest 12 hours in advance.
Transfer learning, a machine learning technique that leverages pre-trained models on large biomedical signal datasets, has further improved model performance. According to Jafari et al. [39], transfer learning has shown notable success in domains such as electrocardiography, electroencephalography, and photoplethysmography, with consistently high classification accuracy reported. This technique enables models to capture complex temporal and morphological features from rich source datasets, which can then be adapted to target pediatric populations, even when labeled data are limited. Importantly, Jafari et al. [39] emphasized that transfer learning not only improves predictive accuracy, but also supports better generalization across diverse patient cohorts, device types, and clinical environments.
Beyond improving predictive accuracy, biosignal AI holds promise for non-invasive monitoring of traditionally invasive parameters. For instance, deep learning models applied to photoplethysmogram signals have been used to estimate arterial blood pressure non-invasively with high accuracy (mean error of –0.006) [29]. Additionally, algorithms trained on capnography-derived end-tidal carbon dioxide data have been shown to estimate arterial carbon dioxide levels, with an R2 coefficient of determination of 0.85 reported using a multilayer perceptron model [32]. Such advances could reduce procedural risks and discomfort for pediatric patients, enabling continuous, high-fidelity monitoring even outside intensive care settings.
However, despite these promising developments, challenges remain. Similar to other AI models based on electronic medical record data, biosignal AI models lack external validation across diverse pediatric populations, require integration with existing hospital workflows, and raise data privacy concerns as well as user acceptability issues such as limited model interpretability [28,39]. Overcoming these barriers is essential to shape the next phase of development.
Among these barriers, limited interpretability stands out as one of the critical challenges for safe clinical adoption, as clinicians need to understand how model predictions are generated in order to act on them with confidence. Without insight into the factors driving a model’s output, there is a risk of relying on opaque algorithms or, conversely, reluctance to act on potentially meaningful alerts. To address this issue, explainable AI could bridge the gap between complex model output and reliable clinical decision-making. As Maurer et al. [40] emphasized, incorporating explainable models into biosignal-based clinical decision support can help clinicians understand why a model makes certain predictions, thereby fostering trust and appropriate action. For example, visualization techniques such as heatmaps and saliency maps that highlight which parts of a biosignal contribute most to a prediction can make AI models more transparent.
In terms of integration into real-world workflows, large language models (LLMs) are being explored as tools to improve communication between AI systems and clinical users. LLMs have the potential to enhance workflow efficiency by translating complex physiological data into structured, clinician-friendly reports. Liu et al. [41] demonstrated that their system, BioSignal Copilot, which integrates LLMs for real-time report generation, can reduce documentation time and improve clinician’s understanding of biosignal-derived insights.
Additionally, the miniaturization of sensors and advances in mobile computing technology are starting to allow wearable and mobile biosignal applications, extending early warning capabilities even beyond hospital walls. Future devices may not only monitor biosignals but interact with AI models on-device, allowing for real-time alerts in home or ambulatory settings. This concept of ubiquitous, intelligent biosignal monitoring has vast implications for reducing preventable deteriorations, especially in resource-limited environments [42].
Lastly, several practical barriers continue to limit real-world implementation. Heterogeneity among electronic monitoring device vendors and the use of proprietary, undisclosed data acquisition protocols create challenges for data interoperability and reliable real-time data flow. Even with improved AI algorithms, alert fatigue remains a major concern, as poorly calibrated or poorly integrated AI systems can unintentionally disrupt clinical workflows. Staffing limitations, specifically the scarcity of clinicians with sufficient understanding of AI-driven analytics, may further hinder widespread and effective utilization. Medico-legal responsibility also remains opaque in many jurisdictions, with unresolved questions about liability when automated predictions influence clinical decisions. Accordingly, the integration of biosignal AI into regulatory, ethical, and clinical governance frameworks is essential, and future systems must ensure robust data security, patient consent, equitable access, and clear clinical accountability. Addressing these operational, technical, and legal barriers will require interdisciplinary collaboration among engineers, clinicians, and regulatory bodies to ensure safe, fair, and impactful deployment of these technologies [43].
Early warning systems in pediatric care have evolved from static scoring tools to dynamic, AI-driven biosignal models. While PEWS and RRS provided the foundation for structured detection and response, emerging technologies offer the potential for earlier, more accurate, and more actionable predictions. Challenges such as generalizability, alarm fatigue, and workflow integration remain, but advances in explainable AI, LLM-based clinical interfaces, and wearable biosignal monitoring devices hold promise for the next generation of pediatric early warning systems. With careful implementation and governance, these innovations may transform pediatric practice and contribute to saving more lives worldwide.
▪ Pediatric early warning systems have progressed from simple score-based tools to data-driven models, yet limitations in accuracy and generalizability remain.
▪ Artificial intelligence and biosignal monitoring enable earlier and more precise detection of deterioration, facilitating more timely clinical responses.
▪ Successful adoption of recent innovations depends on external validation, seamless integration into clinical workflows, and clinician trust through interpretable models.

CONFLICT OF INTEREST

No potential conflict of interest relevant to this article was reported.

FUNDING

None.

ACKNOWLEDGMENTS

None.

AUTHOR CONTRIBUTIONS

Conceptualization: WJ, BL. Data curation: WJ, BL. Formal analysis: WJ, BL. Project administration: WJ, BL. Writing – original draft: WJ, BL. Writing – review & editing: WJ, BL. All authors read and agreed to the published version of the manuscript.

Figure 1.
Evolution of Pediatric Early Warning System (PEWS): intermittent score-based workflows versus continuous artificial intelligence (AI)-driven monitoring. Schematic comparison of intermittent, score-based pediatric early warning workflows and continuous AI-driven monitoring. Traditional systems rely on periodic manual assessment and static scoring, which may delay recognition of clinical deterioration. In contrast, continuous biosignal acquisition with real-time AI analytics enables dynamic risk assessment, actionable alerts, and earlier clinical intervention.
acc-004475f1.jpg
acc-004475f2.jpg
Table 1.
Key milestones in the evolution of early warning and rapid response systems
Year/period Milestone
Pre-1997 Unstructured clinical judgment
1997 Birth of early warning systems
Early 2000s Emergence of RSSs
2004 IHI campaign accelerates RRS adoption
2012 NEWS adopted as a national standard by the NHS (UK)
2020s AI-based EWS models (e.g., DEWS, DeepCARS) introduced

RSS: rapid response system; IHI: Institute for Healthcare Improvement; NEWS: National Early Warning Score; NHS: National Health Service; AI: artificial intelligence; EWS: Early Warning Score; DEWS: Deep learning-based Early Warning Score.

Table 2.
Summary of notable PEWS variants and associated clinical outcomes
Tool/variant Activation Core parameter Country Reported efficacy Validation type
Brighton PEWS (Monaghan 2005) [5] Scoring-based Behavior, respiratory effort, cardiovascular status, vomiting post-surgery, nebulizer use UK Implementation experience Descriptive
Bedside PEWS (Parshuram 2009) [16] Scoring-based SBP, HR, RR, SpO2, CRT, respiratory effort, oxygen therapy Canada Sensitivity 82% Internal (prospective, single center)
Specificity 93%
C-CHEWS (McLellan 2013) [15] Scoring-based Staff concern, parental concern, respiratory effort, behavior, cardiovascular status USA Implementation experience Descriptive
PEWS (Duncan 2006) [12] Scoring-based SBP, HR, RR, SpO2, CRT, BT, GCS, Oxygen therapy Canada Sensitivity 78% Internal (retrospective)
Specificity 95%
Bristol PEWS (Haines 2006) [13] Parameter-based HR, RR, SpO2, seizure, GCS, staff concern UK Sensitivity 99% Internal (prospective, single center)
Specificity 66%
MET Activation Criteria (Tibball 2005) [14] Parameter-based SBP, HR, RR, SpO2, staff concern, consciousness, seizure, respiratory effort, airway threat Australia Cardiac arrest: Risk ratio 1.71 (↓ post-MET), mortality: Risk ratio 2.22 (↓ post-MET) Observational
Modified MET Activation Criteria (Jeon 2023) [3] Parameter-based SBP, HR, RR, SpO2, CRT, consciousness, urine output South Korea Sensitivity 24% Internal (retrospective)
Specificity 99%

PEWS: Pediatric Early Warning Score; SBP: systolic blood pressure; HR: heart rate; RR: respiratory rate; SpO2: oxygen saturation; CRT: capillary refill time; C-CHEWS: Cardiac Children’s Hospital Early Warning Score; BT: body temperature; GCS: Glasgow Coma Scale; MET: medical emergency team.

Table 3.
Recent application of biosignal-based AI models for critical care
Study Signal Setting/population Model/approach Target outcome Reported efficacy
Baek et al. (2024) [29] PPG All ages ANN + RNN Continuous cuffless BP ME as low as -0.006
Coleman et al. (2024) [30] EEG PICU ML multi-stage model Seizure identification F1 score 0.33
Duncan et al. (2020) [31] Wireless HR, RR Pediatric wards RAPID index Clinically significant deterioration events Sensitivity 97%, Specificity 25%
Han et al. (2024) [32] Capnography PICU Multiple ML models Non-invasive PaCO2 estimation R2 coefficient of determination up to 0.85 (XGBoost)
Kallonen et al. (2024) [33] ECG, PPG, RR NICU CNN Late-onset sepsis detection AUROC 0.81
Lai et al. (2024) [34] PPG Adults U-Net Continuous cuffless BP MAE as low as 1.67
Lee et al. (2023) [35] ECG-derived HRV Adult ICU ML (LGBM) In-hospital cardiac arrest AUROC 0.88, AUPRC 0.10
Liu et al. (2024) [36] PPG Adults Ensemble ML Cuffless BP MAE as low as 2.82
Sundrani et al. (2023) [37] ECG, PPG Adult ED Multimodal ML (VitalML) New vital sign abnormalities AUROC up to 0.84 (new tachycardia detection)
Yang et al. (2024) [38] ECG, PPG, RR NICU Multiple ML models Late-onset sepsis risk AUROC up to 0.88 (XGBoost)

AI: artificial intelligence; PPG: photoplethysmography; ANN: artificial neural network; RNN: recurrent neural network; BP: blood pressure; ME: mean error; EEG: electroencephalography; PICU: pediatric intensive care unit; ML: machine learning; HR: heart rate; RR: respiratory rate; RAPID: Real-time Adaptive Predictive Indicator of Deterioration; PaCO2: partial pressure of carbon dioxide; XGBoost: extreme gradient boosting; ECG: electrocardiography; NICU: neonatal intensive care unit; CNN: convolutional neural network; AUROC: area under the receiver operating curve; MAE: mean absolute error; HRV: heart rate variability; ICU: intensive care unit; LGBM: light gradient boosting model; AUPRC: area under the precision-recall curve; ED: emergency department.

  • 1. Al-Harbi S. Impact of rapid response teams on pediatric care: an interrupted time series analysis of unplanned PICU admissions and cardiac arrests. Healthcare (Basel) 2024;12:518.ArticlePubMedPMC
  • 2. AlZaher RA, Jamil S, Murabi I, Ahmari E. Implementation of the bedside paediatric early warning system, its sustainability in clinical practice and patient outcomes: a quality improvement initiative. BMJ Open Qual 2025;14:e002454. ArticlePubMedPMC
  • 3. Jeon YH, Lee B, Kim YS, Jang WJ, Park JD. Eleven years of experience in operating a pediatric rapid response system at a children's hospital in South Korea. Acute Crit Care 2023;38:498-506.ArticlePubMedPMCPDF
  • 4. Roland D. Paediatric Early Warning Scores: holy grail and Achilles' heel. Arch Dis Child Educ Pract Ed 2012;97:208-15.ArticlePubMed
  • 5. Monaghan A. Detecting and managing deterioration in children. Paediatr Nurs 2005;17:32-5.ArticlePubMed
  • 6. Shin Y, Cho KJ, Lee Y, Choi YH, Jung JH, Kim SY, et al. Multicenter validation of a deep-learning-based pediatric early-warning system for prediction of deterioration events. Acute Crit Care 2022;37:654-66.ArticlePubMedPMCPDF
  • 7. Trubey R, Huang C, Lugg-Widger FV, Hood K, Allen D, Edwards D, et al. Validity and effectiveness of paediatric early warning systems and track and trigger tools for identifying and reducing clinical deterioration in hospitalised children: a systematic review. BMJ Open 2019;9:e022105. ArticlePubMedPMC
  • 8. Maharaj R, Raffaele I, Wendon J. Rapid response systems: a systematic review and meta-analysis. Crit Care 2015;19:254.ArticlePMCPDF
  • 9. Hall KK, Lim A, Gale B. The use of rapid response teams to reduce failure to rescue events: a systematic review. J Patient Saf 2020;16:S3-7.ArticlePubMedPMC
  • 10. Chapman SM, Wray J, Oulton K, Peters MJ. Systematic review of paediatric track and trigger systems for hospitalised children. Resuscitation 2016;109:87-109.ArticlePubMed
  • 11. Lambert V, Matthews A, MacDonell R, Fitzsimons J. Paediatric early warning systems for detecting and responding to clinical deterioration in children: a systematic review. BMJ Open 2017;7:e014497. ArticlePubMedPMC
  • 12. Duncan H, Hutchison J, Parshuram CS. The Pediatric Early Warning System score: a severity of illness score to predict urgent medical need in hospitalized children. J Crit Care 2006;21:271-8.ArticlePubMed
  • 13. Haines C, Perrott M, Weir P. Promoting care for acutely ill children-development and evaluation of a paediatric early warning tool. Intensive Crit Care Nurs 2006;22:73-81.ArticlePubMed
  • 14. Tibballs J, van der Jagt EW. Medical emergency and rapid response teams. Pediatr Clin North Am 2008;55:989-1010.ArticlePubMed
  • 15. McLellan MC, Connor JA. The Cardiac Children's Hospital Early Warning Score (C-CHEWS). J Pediatr Nurs 2013;28:171-8.ArticlePubMed
  • 16. Parshuram CS, Hutchison J, Middaugh K. Development and initial validation of the bedside Paediatric Early Warning System score. Crit Care 2009;13:R135.ArticlePubMedPMCPDF
  • 17. Subbe CP, Kruger M, Rutherford P, Gemmel L. Validation of a modified Early Warning Score in medical admissions. QJM 2001;94:521-6.ArticlePubMed
  • 18. Wachter RM, Pronovost PJ. The 100,000 lives campaign: a scientific and policy review. Jt Comm J Qual Patient Saf 2006;32:621-7.ArticlePubMed
  • 19. Smith GB, Prytherch DR, Schmidt PE, Featherstone PI, Higgins B. A review, and performance evaluation, of single-parameter "track and trigger" systems. Resuscitation 2008;79:11-21.ArticlePubMed
  • 20. Lockwood JM, Ziniel SI, Bonafide CP, Brady PW, O'Leary ST, Reese J, et al. Characteristics of pediatric rapid response systems: results from a survey of PRIS hospitals. Hosp Pediatr 2021;11:144-52.ArticlePubMedPDF
  • 21. Foote HP, Shaikh Z, Witt D, Shen T, Ratliff W, Shi H, et al. Development and temporal validation of a machine learning model to predict clinical deterioration. Hosp Pediatr 2024;14:11-20.ArticlePubMedPMCPDF
  • 22. Jeon Y, Kim YS, Jang W, Park JD, Lee B. Development of a deep learning model that predicts critical events of pediatric patients admitted to general wards. Sci Rep 2024;14:4707.ArticlePubMedPMCPDF
  • 23. Park SJ, Cho KJ, Kwon O, Park H, Lee Y, Shim WH, et al. Development and validation of a deep-learning-based pediatric early warning system: a single-center study. Biomed J 2022;45:155-68.ArticlePubMed
  • 24. Churpek MM, Yuen TC, Winslow C, Meltzer DO, Kattan MW, Edelson DP, et al. Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards. Crit Care Med 2016;44:368-74.ArticlePubMedPMC
  • 25. Mao Q, Jay M, Hoffman JL, Calvert J, Barton C, Shimabukuro D, et al. Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ Open 2018;8:e017833. ArticlePubMedPMC
  • 26. Cho KJ, Kim JS, Lee DH, Lee SM, Song MJ, Lim SY, et al. Prospective, multicenter validation of the deep learning-based cardiac arrest risk management system for predicting in-hospital cardiac arrest or unplanned intensive care unit transfer in patients admitted to general wards. Crit Care 2023;27:346.ArticlePubMedPMCPDF
  • 27. Choudhary T, Upadhyaya P, Parvez MZ, Rafi Ahamed S. Editorial: smart biomedical signal analysis with machine intelligence. Front Signal Process 2025;5:1555876.
  • 28. Lee YJ, Park C, Kim H, Cho SJ, Yeo W. Artificial intelligence on biomedical signals: technologies, applications, and future directions. Med X 2024;2:25.ArticlePDF
  • 29. Baek JH, Lee B, Pradana Rachim V, Jang J, Kim S, Kim H, et al. Cuffless blood pressure estimation model using clustering techniques. IEEE Sens J 2024;24:32444-54.Article
  • 30. Coleman K, Fung FW, Topjian A, Abend NS, Xiao R. Optimizing EEG monitoring in critically ill children at risk for electroencephalographic seizures. Seizure 2024;117:244-52.ArticlePubMed
  • 31. Duncan HP, Fule B, Rice I, Sitch AJ, Lowe D. Wireless monitoring and real-time adaptive predictive indicator of deterioration. Sci Rep 2020;10:11366.ArticlePubMedPMCPDF
  • 32. Han HJ, Lee B, Park JD. Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation. BMC Pediatr 2024;24:149.ArticlePubMedPMCPDF
  • 33. Kallonen A, Juutinen M, Värri A, Carrault G, Pladys P, Beuchée A, et al. Early detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: a multicenter prospective development and validation study. Int J Med Inform 2024;184:105366.ArticlePubMed
  • 34. Lai K, Wang X, Cao C. A continuous non-invasive blood pressure prediction method based on deep sparse residual U-Net combined with improved squeeze and excitation skip connections. Sensors (Basel) 2024;24:2721.ArticlePubMedPMC
  • 35. Lee H, Yang HL, Ryu HG, Jung CW, Cho YJ, Yoon SB, et al. Real-time machine learning model to predict in-hospital cardiac arrest using heart rate variability in ICU. NPJ Digit Med 2023;6:215.ArticlePubMedPMCPDF
  • 36. Liu ZD, Li Y, Zhang YT, Zeng J, Chen ZX, Liu JK, et al. HGCTNet: handcrafted feature-guided CNN and transformer network for wearable cuffless blood pressure measurement. IEEE J Biomed Health Inform 2024;28:3882-94.ArticlePubMed
  • 37. Sundrani S, Chen J, Jin BT, Abad ZSH, Rajpurkar P, Kim D, et al. Predicting patient decompensation from continuous physiologic monitoring in the emergency department. NPJ Digit Med 2023;6:60.ArticlePubMedPMCPDF
  • 38. Yang M, Peng Z, van Pul C, Andriessen P, Dong K, Silvertand D, et al. Continuous prediction and clinical alarm management of late-onset sepsis in preterm infants using vital signs from a patient monitor. Comput Methods Programs Biomed 2024;255:108335.ArticlePubMed
  • 39. Jafari M, Tao X, Barua P, Tan R-S, Acharya UR. Application of transfer learning for biomedical signals: a comprehensive review of the last decade (2014-2024). Information Fusion 2025;118:102982.Article
  • 40. Maurer MC, Metsch JM, Hempel P, Bender T, Spicher N. Hauschild AC. Explainable artificial intelligence on biosignals for clinical decision support. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’24); 2024 Aug 25-29; Barcelona, Spain. Association for Computing Machinery. 2024;pp 6597-604.
  • 41. Liu C, Ma Y, Kothur K, Nikpour A, Kavehei O. BioSignal Copilot: leveraging the power of LLMs in drafting reports for biomedical signals. MedRxiv [Preprint] 2023 [cited 2026 Mar 5]. Available from: https://doi.org/10.1101/2023.06.28.23291916. Article
  • 42. Shajari S, Kuruvinashetti K, Komeili A, Sundararaj U. The emergence of ai-based wearable sensors for digital health technology: a review. Sensors (Basel) 2023;23:9498.ArticlePubMedPMC
  • 43. Singh MP, Keche YN. Ethical integration of artificial intelligence in healthcare: narrative review of global challenges and strategic solutions. Cureus 2025;17:e84804. ArticlePubMed

Figure & Data

References

    Citations

    Citations to this article as recorded by  

      • PubReader PubReader
      • ePub LinkePub Link
      • Cite
        CITE
        export Copy
        Close
        Download Citation
        Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.
        Format:
        • RIS — For EndNote, ProCite, RefWorks, and most other reference management software
        • BibTeX — For JabRef, BibDesk, and other BibTeX-specific software
        Include:
        • Citation for the content below
        From scores to signals: evolution and innovations in pediatric early warning systems
        Acute Crit Care. 2026;41(2):252-261.   Published online May 19, 2026
        DOI: https://doi.org/10.4266/acc.004475
        Close
      • XML DownloadXML Download
      Figure
      • 0
      • 1
      From scores to signals: evolution and innovations in pediatric early warning systems
      Image Image
      Figure 1. Evolution of Pediatric Early Warning System (PEWS): intermittent score-based workflows versus continuous artificial intelligence (AI)-driven monitoring. Schematic comparison of intermittent, score-based pediatric early warning workflows and continuous AI-driven monitoring. Traditional systems rely on periodic manual assessment and static scoring, which may delay recognition of clinical deterioration. In contrast, continuous biosignal acquisition with real-time AI analytics enables dynamic risk assessment, actionable alerts, and earlier clinical intervention.
      Graphical abstract

      Figure 1.

      Graphical abstract

      From scores to signals: evolution and innovations in pediatric early warning systems
      Year/period Milestone
      Pre-1997 Unstructured clinical judgment
      1997 Birth of early warning systems
      Early 2000s Emergence of RSSs
      2004 IHI campaign accelerates RRS adoption
      2012 NEWS adopted as a national standard by the NHS (UK)
      2020s AI-based EWS models (e.g., DEWS, DeepCARS) introduced
      Tool/variant Activation Core parameter Country Reported efficacy Validation type
      Brighton PEWS (Monaghan 2005) [5] Scoring-based Behavior, respiratory effort, cardiovascular status, vomiting post-surgery, nebulizer use UK Implementation experience Descriptive
      Bedside PEWS (Parshuram 2009) [16] Scoring-based SBP, HR, RR, SpO2, CRT, respiratory effort, oxygen therapy Canada Sensitivity 82% Internal (prospective, single center)
      Specificity 93%
      C-CHEWS (McLellan 2013) [15] Scoring-based Staff concern, parental concern, respiratory effort, behavior, cardiovascular status USA Implementation experience Descriptive
      PEWS (Duncan 2006) [12] Scoring-based SBP, HR, RR, SpO2, CRT, BT, GCS, Oxygen therapy Canada Sensitivity 78% Internal (retrospective)
      Specificity 95%
      Bristol PEWS (Haines 2006) [13] Parameter-based HR, RR, SpO2, seizure, GCS, staff concern UK Sensitivity 99% Internal (prospective, single center)
      Specificity 66%
      MET Activation Criteria (Tibball 2005) [14] Parameter-based SBP, HR, RR, SpO2, staff concern, consciousness, seizure, respiratory effort, airway threat Australia Cardiac arrest: Risk ratio 1.71 (↓ post-MET), mortality: Risk ratio 2.22 (↓ post-MET) Observational
      Modified MET Activation Criteria (Jeon 2023) [3] Parameter-based SBP, HR, RR, SpO2, CRT, consciousness, urine output South Korea Sensitivity 24% Internal (retrospective)
      Specificity 99%
      Study Signal Setting/population Model/approach Target outcome Reported efficacy
      Baek et al. (2024) [29] PPG All ages ANN + RNN Continuous cuffless BP ME as low as -0.006
      Coleman et al. (2024) [30] EEG PICU ML multi-stage model Seizure identification F1 score 0.33
      Duncan et al. (2020) [31] Wireless HR, RR Pediatric wards RAPID index Clinically significant deterioration events Sensitivity 97%, Specificity 25%
      Han et al. (2024) [32] Capnography PICU Multiple ML models Non-invasive PaCO2 estimation R2 coefficient of determination up to 0.85 (XGBoost)
      Kallonen et al. (2024) [33] ECG, PPG, RR NICU CNN Late-onset sepsis detection AUROC 0.81
      Lai et al. (2024) [34] PPG Adults U-Net Continuous cuffless BP MAE as low as 1.67
      Lee et al. (2023) [35] ECG-derived HRV Adult ICU ML (LGBM) In-hospital cardiac arrest AUROC 0.88, AUPRC 0.10
      Liu et al. (2024) [36] PPG Adults Ensemble ML Cuffless BP MAE as low as 2.82
      Sundrani et al. (2023) [37] ECG, PPG Adult ED Multimodal ML (VitalML) New vital sign abnormalities AUROC up to 0.84 (new tachycardia detection)
      Yang et al. (2024) [38] ECG, PPG, RR NICU Multiple ML models Late-onset sepsis risk AUROC up to 0.88 (XGBoost)
      Table 1. Key milestones in the evolution of early warning and rapid response systems

      RSS: rapid response system; IHI: Institute for Healthcare Improvement; NEWS: National Early Warning Score; NHS: National Health Service; AI: artificial intelligence; EWS: Early Warning Score; DEWS: Deep learning-based Early Warning Score.

      Table 2. Summary of notable PEWS variants and associated clinical outcomes

      PEWS: Pediatric Early Warning Score; SBP: systolic blood pressure; HR: heart rate; RR: respiratory rate; SpO2: oxygen saturation; CRT: capillary refill time; C-CHEWS: Cardiac Children’s Hospital Early Warning Score; BT: body temperature; GCS: Glasgow Coma Scale; MET: medical emergency team.

      Table 3. Recent application of biosignal-based AI models for critical care

      AI: artificial intelligence; PPG: photoplethysmography; ANN: artificial neural network; RNN: recurrent neural network; BP: blood pressure; ME: mean error; EEG: electroencephalography; PICU: pediatric intensive care unit; ML: machine learning; HR: heart rate; RR: respiratory rate; RAPID: Real-time Adaptive Predictive Indicator of Deterioration; PaCO2: partial pressure of carbon dioxide; XGBoost: extreme gradient boosting; ECG: electrocardiography; NICU: neonatal intensive care unit; CNN: convolutional neural network; AUROC: area under the receiver operating curve; MAE: mean absolute error; HRV: heart rate variability; ICU: intensive care unit; LGBM: light gradient boosting model; AUPRC: area under the precision-recall curve; ED: emergency department.

      Table 1.

      Table 2.

      Table 3.

      ACC : Acute and Critical Care
      © The Korean Society of Critical Care Medicine.
      TOP